import os
import numpy as np
import pandas as pd

# TensorFlow
import tensorflow as tf
from tensorflow.keras import layers, models

# cv
import cv2

# Visualisation libraries

## Text
from colorama import Fore, Back, Style
from IPython.display import Image, display, Markdown, Latex, clear_output

## progressbar
import progressbar

## plotly
from plotly.offline import init_notebook_mode, iplot 
import plotly.graph_objs as go
import plotly.offline as py
from plotly.subplots import make_subplots
import plotly.express as px

## seaborn
import seaborn as sns

## matplotlib
import matplotlib.pyplot as plt
from matplotlib.patches import Ellipse, Polygon
from matplotlib.font_manager import FontProperties
import matplotlib.colors as mcolors
from matplotlib.colors import LinearSegmentedColormap
from mpl_toolkits.axes_grid1.inset_locator import inset_axes
from matplotlib import cm
plt.style.use('seaborn-whitegrid')
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12
plt.rcParams['text.color'] = 'k'
%matplotlib inline

import warnings
warnings.filterwarnings("ignore")

Home / Healthcare Analytics and Modeling

Melanoma Detection

• Preprocessing and Exploratory Data Analysis
• Modeling: Keras Multi-layer Perceptron (MLP) for Image Classifications

Skin Lesion Analysis Towards Melanoma Detection

Dataset Description

Training neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available datasets of dermatoscopic images. We tackle this problem by releasing the HAM10000 ("Human Against Machine with 10000 training images") dataset. We collected dermatoscopic images from different populations, acquired and stored by different modalities. The final dataset consists of 10015 dermatoscopic images which can serve as a training set for academic machine learning purposes. Cases include a representative collection of all important diagnostic categories in the realm of pigmented lesions: Actinic keratoses and intraepithelial carcinoma / Bowen's disease (akiec), basal cell carcinoma (bcc), benign keratosis-like lesions (solar lentigines / seborrheic keratoses and lichen-planus like keratoses, bkl), dermatofibroma (df), melanoma (mel), melanocytic nevi (nv) and vascular lesions (angiomas, angiokeratomas, pyogenic granulomas and hemorrhage, vasc).

More than 50% of lesions are confirmed through histopathology (histo), the ground truth for the rest of the cases is either follow-up examination (follow_up), expert consensus (consensus), or confirmation by in-vivo confocal microscopy (confocal). The dataset includes lesions with multiple images, which can be tracked by the lesion_id-column within the HAM10000_metadata file.

Due to upload size limitations, images are stored in two files:

* HAM10000_images_part1.zip (5000 JPEG files)
* HAM10000_images_part2.zip (5015 JPEG files)

Additional data for evaluation purposes

The HAM10000 dataset served as the training set for the ISIC 2018 challenge (Task 3). The test-set images are available herein as ISIC2018_Task3_Test_Images.zip (1511 images), the official validation-set is available through the challenge website https://challenge2018.isic-archive.com/. The ISIC-Archive also provides a "Live challenge" submission site for continuous evaluation of automated classifiers on the official validation- and test-set.

Comparison to physicians

Test-set evaluations of the ISIC 2018 challenge were compared to physicians on an international scale, where the majority of challenge participants outperformed expert readers: Tschandl P. et al., Lancet Oncol 2019

Human-computer collaboration

The test-set images were also used in a study comparing different methods and scenarios of human-computer collaboration: Tschandl P. et al., Nature Medicine 2020 Following corresponding metadata is available herein:

• ISIC2018_Task3_Test_NatureMedicine_AI_Interaction_Benefit.csv: Human ratings for Test images with and without interaction with a ResNet34 CNN (Malignancy Probability, Multi-Class probability, CBIR) or Human-Crowd Multi-Class probabilities. This is data was collected for and analyzed in Tschandl P. et al., Nature Medicine 2020, therefore please refer to this publication when using the data.
• HAM10000_segmentations_lesion_tschandl.zip: To evaluate regions of CNN activations in Tschandl P. et al., Nature Medicine 2020 (please refer to this publication when using the data), a single dermatologist (Tschandl P) created binary segmentation masks for all 10015 images from the HAM10000 dataset. Masks were initialized with the segmentation network as described by Tschandl et al., Computers in Biology and Medicine 2019, and the following verified, corrected, or replaced via the free-hand selection tool in FIJI.

Dataset

def Path_Tree(PATH, Extension):
    Out = {}
    sep = ' ' * 3
    BACK = {'Black': Back.BLACK, 'Red':Back.RED, 'Green':Back.GREEN, 'Yellow': Back.YELLOW, 'Blue': Back.BLUE,
         'Magenta':Back.MAGENTA, 'Cyan': Back.CYAN}
    title = PATH.split('\\')[-1]
    print(Style.RESET_ALL + Fore.BLUE + Style.NORMAL + '=' * (len(title) +1) + Style.RESET_ALL)
    print(Back.BLACK + Fore.CYAN + Style.NORMAL + title+':'+ Style.RESET_ALL)
    print(Style.RESET_ALL + Fore.BLUE + Style.NORMAL + '=' * (len(title) +1)+ Style.RESET_ALL)
    i = 0
    C = ['Red', 'Green', 'Yellow', 'Blue', 'Magenta', 'Cyan']*len(os.listdir(PATH))
    for entry in os.listdir(PATH):
        if os.path.isdir(PATH):
            print('└──',BACK[C[i]] + Fore.BLACK + Style.NORMAL + entry+':'+ Style.RESET_ALL)
            Sub = os.path.join (PATH, entry)
            List = os.listdir(Sub)
            List = [x for x in List if x.endswith(Extension)]
            Out[entry] = List
            print(2* sep, Fore.BLUE + Style.NORMAL +
                          '%i %s files:' % (len(List), List[0].split('.')[-1].upper()) + Style.RESET_ALL)
            print(2* sep, ', '.join(List[:5]) + ', ...')
            i+=1
    return Out


Path = 'slatmd_mod'
Files_dict = Path_Tree(Path, '.jpg')

Labels_dict = {'akiec': 'Actinic Keratoses and Intraepithelial Carcinoma',
               'bcc': 'Basal Cell Carcinoma',
               'bkl': 'Benign Keratosis-like Lesions',
               'df': 'Dermatofibroma',
               'mel': 'Melanoma',
               'nv': 'Melanocytic Nevi',
               'vasc': 'Vascular Lesions'}

===========
slatmd_mod:
===========
└── akiec:
       327 JPG files:
       ISIC_0024329.jpg, ISIC_0024372.jpg, ISIC_0024418.jpg, ISIC_0024450.jpg, ISIC_0024463.jpg, ...
└── bcc:
       514 JPG files:
       ISIC_0024331.jpg, ISIC_0024332.jpg, ISIC_0024345.jpg, ISIC_0024360.jpg, ISIC_0024403.jpg, ...
└── bkl:
       1099 JPG files:
       ISIC_0024312.jpg, ISIC_0024324.jpg, ISIC_0024336.jpg, ISIC_0024337.jpg, ISIC_0024338.jpg, ...
└── df:
       115 JPG files:
       ISIC_0024318.jpg, ISIC_0024330.jpg, ISIC_0024386.jpg, ISIC_0024396.jpg, ISIC_0024553.jpg, ...
└── mel:
       1113 JPG files:
       ISIC_0024310.jpg, ISIC_0024313.jpg, ISIC_0024315.jpg, ISIC_0024323.jpg, ISIC_0024333.jpg, ...
└── nv:
       6705 JPG files:
       ISIC_0024306.jpg, ISIC_0024307.jpg, ISIC_0024308.jpg, ISIC_0024309.jpg, ISIC_0024311.jpg, ...
└── vasc:
       142 JPG files:
       ISIC_0024370.jpg, ISIC_0024375.jpg, ISIC_0024402.jpg, ISIC_0024475.jpg, ISIC_0024662.jpg, ...

batch_size = 128
Img_Height = 180
Img_Width = 180

train_ds = tf.keras.preprocessing.image_dataset_from_directory(directory= Path, validation_split=0.2, subset="training",
                                                               seed=123, image_size=(Img_Height, Img_Width),
                                                               batch_size=batch_size)
val_ds = tf.keras.preprocessing.image_dataset_from_directory(directory= Path, validation_split=0.2, subset="validation",
                                                             seed=123, image_size=(Img_Height, Img_Width),
                                                             batch_size=batch_size)

Found 10015 files belonging to 7 classes.
Using 8012 files for training.
Found 10015 files belonging to 7 classes.
Using 2003 files for validation.

fig, ax = plt.subplots(5, 5 , figsize = (16, 16))
ax = ax.ravel()
class_names = train_ds.class_names
Colors = dict(zip(np.arange(len(Labels_dict.keys())), mcolors.TABLEAU_COLORS.values()))
for images, labels in train_ds.take(1):
    for i in range(len(ax)):
        _ = ax[i].imshow(images[i].numpy().astype("uint8"))
        _ = ax[i].set_title(Labels_dict[class_names[labels[i]]],
                            fontweight='bold', fontsize = 10.5, color = Colors[labels[i].numpy()])
        _ = ax[i].axis("off")
        _ = ax[i].set_aspect(1)

Modeling: Keras Multi-layer Perceptron (MLP) for Image Classifications

A multi-layer perceptron (MLP) is a class of feedforward artificial neural network (ANN). The algorithm at each iteration uses the Cross-Entropy Loss to measure the loss, and then the gradient and the model update is calculated. At the end of this iterative process, we would reach a better level of agreement between test and predicted sets since the error would be lower from that of the first step.

model = models.Sequential([layers.experimental.preprocessing.Rescaling(1./255, input_shape=(Img_Height, Img_Width, 3)),
                           layers.Conv2D(16, 3, padding='same', activation='relu'),
                           layers.MaxPooling2D(),
                           layers.Conv2D(32, 3, padding='same', activation='relu'),
                           layers.MaxPooling2D(),
                           layers.Conv2D(64, 3, padding='same', activation='relu'),
                           layers.MaxPooling2D(),
                           layers.Flatten(),
                           layers.Dense(128, activation='relu'),
                           layers.Dense(len(Labels_dict))])
model.summary()
tf.keras.utils.plot_model(model, show_shapes=True, show_layer_names=True, expand_nested = True)

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
rescaling (Rescaling)        (None, 180, 180, 3)       0         
_________________________________________________________________
conv2d (Conv2D)              (None, 180, 180, 16)      448       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 90, 90, 16)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 90, 90, 32)        4640      
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 45, 45, 32)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 45, 45, 64)        18496     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 22, 22, 64)        0         
_________________________________________________________________
flatten (Flatten)            (None, 30976)             0         
_________________________________________________________________
dense (Dense)                (None, 128)               3965056   
_________________________________________________________________
dense_1 (Dense)              (None, 7)                 903       
=================================================================
Total params: 3,989,543
Trainable params: 3,989,543
Non-trainable params: 0
_________________________________________________________________

Compiling and fitting the model

# Number of iterations
IT = 11

model.compile(optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])

# Training the model
history = model.fit(train_ds, validation_data=val_ds, epochs=IT, verbose = 0)

def Search_List(Key, List): return [s for s in List if Key in s]

Metrics_Names = {'loss':'Loss', 'accuracy':'Accuracy', 'mae':'MAE', 'mse':'MSE', 'recall': 'Recall'}

def Table_modify(df, Metrics_Names = Metrics_Names):
    df = df.rename(columns = Metrics_Names)
    df = df.reindex(sorted(df.columns), axis=1)
    df.insert(loc = 0, column = 'Iteration', value = np.arange(0, df.shape[0]), allow_duplicates=False)
    return df

Validation_Table = Search_List('val_',history.history.keys()) 
Train_Table = list(set( history.history.keys()) - set(Validation_Table))
Validation_Table = pd.DataFrame(np.array([history.history[x] for x in Validation_Table]).T, columns = Validation_Table)
Train_Table = pd.DataFrame(np.array([history.history[x] for x in Train_Table]).T, columns = Train_Table)
Validation_Table.columns = [x.replace('val_','') for x in Validation_Table.columns]

Train_Table = Table_modify(Train_Table)
Validation_Table = Table_modify(Validation_Table)

# Train Set Score
score = model.evaluate(train_ds, batch_size = batch_size, verbose = 0)
score = pd.DataFrame(score, index = model.metrics_names).T
score.index = ['Train Set Score']
# Validation Set Score
Temp = model.evaluate(val_ds, batch_size = batch_size, verbose = 0) 
Temp = pd.DataFrame(Temp, index = model.metrics_names).T
Temp.index = ['Validation Set Score']
score = score.append(Temp)
score.rename(columns= Metrics_Names, inplace = True)
score = score.reindex(sorted(score.columns), axis=1)
display(score.style.set_precision(4))

	Accuracy	Loss
Train Set Score	0.8389	0.4545
Validation Set Score	0.7424	0.7535

def Plot_history(history, PD, Title = False, metrics_names = [x.title() for x in model.metrics_names]):
    fig = make_subplots(rows=1, cols=2, horizontal_spacing = 0.02, column_widths=[0.6, 0.4],
                        specs=[[{"type": "scatter"},{"type": "table"}]])
    # Left
    Colors = ['OrangeRed', 'MidnightBlue', 'purple']
    for j in range(len(metrics_names)):
        fig.add_trace(go.Scatter(x= history['Iteration'].values, y= history[metrics_names[j]].values,
                                 line=dict(color=Colors[j], width= 1.5), name = metrics_names[j]), 1, 1)
    fig.update_layout(legend=dict(x=0, y=1.1, traceorder='reversed', font_size=12),
                  dragmode='select', plot_bgcolor= 'white', height=600, hovermode='closest',
                  legend_orientation='h')
    fig.update_xaxes(range=[history.Iteration.min(), history.Iteration.max()],
                     showgrid=True, gridwidth=1, gridcolor='Lightgray',
                     showline=True, linewidth=1, linecolor='Lightgray', mirror=True, row=1, col=1)
    fig.update_yaxes(range=[0, PD['yLim']], showgrid=True, gridwidth=1, gridcolor='Lightgray',
                     showline=True, linewidth=1, linecolor='Lightgray', mirror=True, row=1, col=1)
    # Right
    if not PD['Table_Rows'] == None:
        ind = np.linspace(0, history.shape[0], PD['Table_Rows'], endpoint = False).round(0).astype(int)
        ind = np.append(ind, history.index[-1])
        history = history[history.index.isin(ind)]
    T = history.copy()
    T[metrics_names] = T[metrics_names].applymap(lambda x: '%.4e' % x)
    Temp = []
    for i in T.columns:
        Temp.append(T.loc[:,i].values)
    TableColors = PD['TableColors']
    fig.add_trace(go.Table(header=dict(values = list(history.columns), line_color=TableColors[0],
                   fill_color=TableColors[0], align=['center','center'], font=dict(color=TableColors[1], size=12), height=25),
                   columnwidth = PD['tablecolumnwidth'], cells=dict(values=Temp, line_color=TableColors[0],
                      fill=dict(color=[TableColors[1], TableColors[1]]),
                      align=['center', 'center'], font_size=12,height=20)), 1, 2)
    if Title != False:
        fig.update_layout(plot_bgcolor= 'white',
                      title={'text': Title, 'x':0.46, 'y':0.94, 'xanchor': 'center', 'yanchor': 'top'},
                          yaxis_title='Frequency')
    fig.show()

PD = dict(Table_Rows = 25, yLim = 1.2, tablecolumnwidth = [0.3, 0.4, 0.4], TableColors = ['Navy','White'])
Plot_history(Train_Table, Title = 'Train Set', PD = PD)
Plot_history(Validation_Table, Title = 'Validation Set', PD = PD)

Here, we only went through a few iterations; however, we need to train the model for more iterations to get more accurate results.

---

References

1. Kaggle Dataset: Skin Cancer MNIST: HAM10000
2. Skin Lesion Analysis Towards Melanoma Detection
3. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions
4. Codella, Noel, et al. "Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic)." arXiv preprint arXiv:1902.03368 (2019).

---